Publication
Multi-agent exploration of unknown terrain: Combining neural time series forecasting with multi-agent coordination for planetary surface exploration
| datacite.subject.fos | Engenharia e Tecnologia | |
| datacite.subject.sdg | 09:Indústria, Inovação e Infraestruturas | |
| dc.contributor.advisor | Conceição, Luís Manuel Silva Conceição | |
| dc.contributor.author | VIEGAS, IVAN MANUEL ESTEVÃO | |
| dc.date.accessioned | 2025-11-14T16:00:32Z | |
| dc.date.available | 2025-11-14T16:00:32Z | |
| dc.date.issued | 2025-10-14 | |
| dc.description.abstract | This work addresses the challenge of autonomous robotic exploration in uncertain planetary environments, such as the Martian surface, where long communication delays with Earth make local decision-making essential. The main objective was to develop a simulation framework aimed at enhancing the efficiency and autonomy of multi-agent robotic systems, with a particular emphasis on scalable cooperation. The study investigates how the integration of Multi-Agent Reinforcement Learning (MARL) algorithms and dynamic environmental simulations can improve exploration in unknown terrains. The methodology involved the development of a detailed 2D simulation environment of Jezero Crater, Mars, incorporating realistic weather conditions modeled from the MEDA dataset. Climate forecasting relied on N-BEATS and LSTM models, with N-BEATS demonstrating superior performance in predicting environmental variables. Coordination between Explorer agents (tasked with mapping and sample identification) and Transporter agents (responsible for collection and delivery) was managed through an Auction-Based Coordination and Autonomy Layer powered by MARL. The results demonstrate the effectiveness of the multi-agent approach, achieving a successful coordination rate of 79.4% across multiple simulation runs under varying atmospheric conditions (with successful coordination defined as task assignments completed within the mission time budget via the auction-based mechanism). Furthermore, emergent behavioral specialization was observed among Transporter agents, with significant diversity in the confidence_ bias parameter (coefficient of variation, CV = 0.256), enhancing overall system robustness. Additionally, the system exhibited linear scalability and a 192.9% improvement in territorial coverage in multi-agent configurations compared to single-agent setups. In conclusion, the integration of MARL with dynamic environmental simulations provides a robust and adaptable solution to the complex challenges of robotic exploration and navigation in extreme environments, paving the way for future autonomous space missions. | eng |
| dc.identifier.tid | 204033560 | |
| dc.identifier.uri | http://hdl.handle.net/10400.22/30916 | |
| dc.language.iso | eng | |
| dc.rights.uri | N/A | |
| dc.subject | Multi-Agent Reinforcement Learning | |
| dc.subject | Autonomous Robotic Exploration | |
| dc.subject | Surface of Mars | |
| dc.subject | Multi-Agent Coordination | |
| dc.subject | Time Series Forecasting | |
| dc.subject | Dynamic Environmental Simulation | |
| dc.title | Multi-agent exploration of unknown terrain: Combining neural time series forecasting with multi-agent coordination for planetary surface exploration | eng |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| thesis.degree.name | Mestrado em Engenharia de Inteligência Artificial |